Heng666 commited on
Commit
7276e50
1 Parent(s): 04d6ffb

Upload MistralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +25 -0
  2. generation_config.json +6 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "taiwan-mistral-300M-wiki",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "eos_token_id": 0,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 1024,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 2400,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 16,
15
+ "num_hidden_layers": 24,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 1024,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.35.2",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.35.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0d6320674cf88e28f71b0320ae0bb8ee9a56e44a36d1d2b71e3729cf10bf53
3
+ size 1272148192